☆316Jan 12, 2026Updated 6 months ago
Alternatives and similar repositories for emergent-misalignment
Users that are interested in emergent-misalignment are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code repo for the model organisms and convergent directions of EM papers.☆72Sep 22, 2025Updated 10 months ago
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆452Apr 22, 2026Updated 3 months ago
- ☆58Jun 26, 2025Updated last year
- ☆37Feb 20, 2025Updated last year
- ☆152Feb 10, 2026Updated 5 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- A python sdk for LLM finetuning and inference on runpod infrastructure☆30May 12, 2026Updated 2 months ago
- Code and materials for "Weird Generalization and Inductive Backdoors"☆41Jan 11, 2026Updated 6 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆78Updated this week
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆33May 23, 2024Updated 2 years ago
- Inference API for many LLMs and other useful tools for empirical research☆134May 29, 2026Updated last month
- Improving Alignment and Robustness with Circuit Breakers☆266Sep 24, 2024Updated last year
- Representation Engineering: A Top-Down Approach to AI Transparency☆1,013Aug 14, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,484Updated this week
- ☆50Jul 4, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away fro…☆158Jan 20, 2026Updated 6 months ago
- ☆28Sep 5, 2024Updated last year
- ☆20Jan 7, 2026Updated 6 months ago
- ☆114Aug 8, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,712Updated this week
- Situational Awareness Dataset☆52Dec 14, 2024Updated last year
- ☆95Apr 18, 2026Updated 3 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆29Nov 20, 2024Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆998Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Code for Negation Neglect☆16May 22, 2026Updated 2 months ago
- [EMNLP 2025] Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment☆15Jul 22, 2025Updated last year
- ☆95Oct 8, 2025Updated 9 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 8 months ago
- James' cookbook of evaluations and finetuning experiments☆32Feb 19, 2026Updated 5 months ago
- ☆39Jul 9, 2025Updated last year
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆31Feb 11, 2025Updated last year
- ☆31Nov 11, 2025Updated 8 months ago
- Code for SafeMERGE (ICLR 2025).☆15Apr 1, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆17Mar 16, 2026Updated 4 months ago
- ☆20Nov 15, 2024Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆424Jun 13, 2025Updated last year
- WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…☆176May 29, 2025Updated last year
- ☆42May 21, 2025Updated last year
- ☆19Dec 29, 2025Updated 6 months ago
- Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"☆61Jan 15, 2025Updated last year